© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 1596
    Prev
    Next
    INDEX
    Explanations

    code syntax, programming languages

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron strongly activates on multi‐digit numeric literals (e.g. “1600”), i.e. it picks out sequences of digits.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     This
    0.46
     It
    0.45
    면
    0.42
     These
    0.42
     There
    0.40
     They
    0.40
     例文帳に追加
    0.40
     これは
    0.39
    です
    0.38
     є
    0.38
    POSITIVE LOGITS
    {//
    0.48
    //{
    0.43
    gzip
    0.42
    "./
    0.42
    {
    0.42
    ون
    0.41
    καν
    0.40
    ()){
    0.39
    registro
    0.39
    (“
    0.39
    Activations Density 0.000%

    No Known Activations